[bbc] Add support for direct bbc.co.uk embeds

This commit is contained in:
Sergey M․ 2015-07-27 22:05:51 +06:00
parent 4c6bd5b5b6
commit 88ed52aec9
2 changed files with 30 additions and 12 deletions

View file

@ -450,6 +450,14 @@ class BBCIE(BBCCoUkIE):
}, },
'playlist_count': 9, 'playlist_count': 9,
'skip': 'Save time', 'skip': 'Save time',
}, {
# article with multiple videos embedded with `new SMP()`
'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460',
'info_dict': {
'id': '3662a707-0af9-3149-963f-47bea720b460',
'title': 'BBC Blogs - Adam Curtis - BUGGER',
},
'playlist_count': 18,
}, { }, {
# single video embedded with mediaAssetPage.init() # single video embedded with mediaAssetPage.init()
'url': 'http://www.bbc.com/news/world-europe-32041533', 'url': 'http://www.bbc.com/news/world-europe-32041533',
@ -637,12 +645,30 @@ def _real_extract(self, url):
playlist_title = self._html_search_regex( playlist_title = self._html_search_regex(
r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'playlist title') r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'playlist title')
playlist_description = self._og_search_description(webpage) playlist_description = self._og_search_description(webpage, default=None)
def extract_all(pattern):
return list(filter(None, map(
lambda s: self._parse_json(s, playlist_id, fatal=False),
re.findall(pattern, webpage))))
# Multiple video article (e.g.
# http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]*)?'
entries = []
for match in extract_all(r'new\s+SMP\(({.+?})\)'):
embed_url = match.get('playerSettings', {}).get('externalEmbedUrl')
if embed_url and re.match(EMBED_URL, embed_url):
entries.append(embed_url)
entries.extend(re.findall(
r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage))
if entries:
return self.playlist_result(
[self.url_result(entry, 'BBCCoUk') for entry in entries],
playlist_id, playlist_title, playlist_description)
# Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511) # Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511)
medias = list(filter(None, map( medias = extract_all(r"data-media-meta='({[^']+})'")
lambda s: self._parse_json(s, playlist_id, fatal=False),
re.findall(r"data-media-meta='({[^']+})'", webpage))))
if not medias: if not medias:
# Single video article (e.g. http://www.bbc.com/news/video_and_audio/international) # Single video article (e.g. http://www.bbc.com/news/video_and_audio/international)

View file

@ -276,14 +276,6 @@ class GenericIE(InfoExtractor):
'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.', 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
}, },
}, },
# BBC iPlayer embeds
{
'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER',
'info_dict': {
'title': 'BBC - Blogs - Adam Curtis - BUGGER',
},
'playlist_mincount': 18,
},
# RUTV embed # RUTV embed
{ {
'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html', 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',